.. DO NOT EDIT.
.. THIS FILE WAS AUTOMATICALLY GENERATED BY SPHINX-GALLERY.
.. TO MAKE CHANGES, EDIT THE SOURCE PYTHON FILE:
.. "auto_examples/demo_agents/video_plot_mbqvi.py"
.. LINE NUMBERS ARE GIVEN BELOW.

.. only:: html

    .. note::
        :class: sphx-glr-download-link-note

        :ref:`Go to the end <sphx_glr_download_auto_examples_demo_agents_video_plot_mbqvi.py>`
        to download the full example code

.. rst-class:: sphx-glr-example-title

.. _sphx_glr_auto_examples_demo_agents_video_plot_mbqvi.py:


==================================================
A demo of MBQVI algorithm in Gridworld environment
==================================================
 Illustration of how to set up an MBQVI algorithm in rlberry.
 The environment chosen here is GridWorld environment.

.. video:: ../../video_plot_mbqvi.mp4
   :width: 600

.. GENERATED FROM PYTHON SOURCE LINES 12-34

.. code-block:: python3

    from rlberry_scool.agents.mbqvi import MBQVIAgent
    from rlberry_research.envs.finite import GridWorld

    params = {}
    params["n_samples"] = 100  # samples per state-action pair
    params["gamma"] = 0.99
    params["horizon"] = None

    env = GridWorld(7, 10, walls=((2, 2), (3, 3)), success_probability=0.6)
    agent = MBQVIAgent(env, **params)
    info = agent.fit()
    print(info)

    # evaluate policy in a deterministic version of the environment
    env_eval = GridWorld(7, 10, walls=((2, 2), (3, 3)), success_probability=1.0)
    env_eval.enable_rendering()
    state, info = env_eval.reset()
    for tt in range(50):
        action = agent.policy(state)
        next_s, _, _, _, _ = env_eval.step(action)
        state = next_s
    video = env_eval.save_video("_video/video_plot_mbqvi.mp4")


.. rst-class:: sphx-glr-timing

   **Total running time of the script:** (0 minutes 0.000 seconds)


.. _sphx_glr_download_auto_examples_demo_agents_video_plot_mbqvi.py:

.. only:: html

  .. container:: sphx-glr-footer sphx-glr-footer-example




    .. container:: sphx-glr-download sphx-glr-download-python

      :download:`Download Python source code: video_plot_mbqvi.py <video_plot_mbqvi.py>`

    .. container:: sphx-glr-download sphx-glr-download-jupyter

      :download:`Download Jupyter notebook: video_plot_mbqvi.ipynb <video_plot_mbqvi.ipynb>`


.. only:: html

 .. rst-class:: sphx-glr-signature

    `Gallery generated by Sphinx-Gallery <https://sphinx-gallery.github.io>`_